Showing 2026Show all
2 papers · 1 filter
cs.AI2026
VideoMM: Adaptive Macro-Micro Inference for Efficient Video MLLMs
Haoyu Guo, Yuan Feng, Junlin Lv +3
Scaling Multimodal Large Language Models (MLLMs) to long-form video understanding is bottlenecked by the explosion of visual tokens, which saturates context windows and incurs proh…
cs.CL2026
LibraSpec: Dynamic Diffusion-Based Speculative Decoding via Marginal-Gain-Driven Optimization
Zexun Lin, Yuan Feng, Junlin Lv +2
Speculative decoding accelerates large language model inference by drafting multiple tokens for parallel verification, with efficiency critically determined by the speculative leng…